# Import necessary libraries
import numpy as np
from reservoirpy import nodes, datasets, observables
import reservoirpy as rpy
rpy.verbosity(0)
#rpy.set_seed(42)
import hierarchical_genomes as hg
import networkx as nx
import matplotlib.pyplot as plt
import copy
import random
#import json

# Loading configuration
#with open('config.json', 'r') as config_file:
#    config = json.load(config_file)

# Example of accessing a config value
#population_size = config['population_size']


# Import functions from helper file
from expt_helper_functions import create_initial_genome, select_best_genomes, reproduce, log_generation_results, analyze_results,mae,mse,calculate_diversity_score, should_increase_timestep,visualize_genome

# Set up the main parameters
population_size = 100 #50
n_generations =    200  #100
mutation_probability = 0.1
insertion_probability = 0.1

# Define the number of input and output nodes for your neural network
#num_input_nodes = 10  
#num_output_nodes = 10  

# Load the Mackey-Glass dataset with specified timesteps
n_timesteps = 2000  
X = datasets.mackey_glass(n_timesteps=n_timesteps, sample_len=2000)
num_input_nodes = X.shape[1]  # Dynamically set based on the number of features in X
num_output_nodes = 1
train_end = int(len(X) * 0.7)
test_start = train_end + 1


# Automatic timestep calculation
train_split = 0.5
train_timesteps = int(train_split * n_timesteps)
test_timesteps = train_timesteps + 1
timestep_increment = 10

elitism_factor = 0.1  # Assuming you want to carry over 10% of the population
num_elites = int(elitism_factor * population_size)





# Initialize your population
genome_population = [create_initial_genome() for _ in range(population_size)]

# Define a fitness evaluation function
def evaluate_fitness(genome):
    # Convert genome to neural network (function from your thesis code)
    weight_matrix = hg.transcribe_hierarchical_genome_to_weight_matrix(genome)
    
    # Setup the Echo State Network
    #esn = nodes.Reservoir(W=weight_matrix) >> nodes.Ridge(ridge=1e-6)
    
    # Setup the Echo State Network with explicit Win and bias
    #esn = nodes.Reservoir(Win=np.ones((num_input_nodes, 1)), W=weight_matrix, bias=np.zeros((len(weight_matrix), 1))) >> nodes.Ridge(ridge=1e-6)
    
    num_reservoir_nodes = weight_matrix.shape[0]  # Assuming weight_matrix is a square matrix
    num_input_features = 1  # Adjust based on your specific input features

    # Setup the Echo State Network with adjusted Win and bias
    esn = nodes.Reservoir(Win=np.ones((num_reservoir_nodes, num_input_features)), W=weight_matrix, bias=np.zeros((num_reservoir_nodes, 1))) >> nodes.Ridge(ridge=1e-6)


    # Train and forecast using the ESN
    #forecast = esn.fit(X[:500], X[1:501]).run(X[503:])
    
    # Calculate fitness (e.g., using RMSE)
    #fitness_score = observables.rmse(forecast, X[503:])
    
    # Train and forecast using the ESN
    forecast = esn.fit(X[:train_end], X[1:train_end+1]).run(X[test_start:])
    
    # Calculate fitness (using RMSE and MAE)
    fitness_rmse = observables.rmse(forecast, X[test_start:])
    fitness_mae = mae(forecast, X[test_start:])
    fitness_mse = mse(forecast, X[test_start:])
    
    
    return {'rmse': fitness_rmse, 'mae': fitness_mae, 'mse': fitness_mse}

    #complexity_penalty = len(genome) * 0.05 #complexity_penalty_rate (0.01 to 0.05)  # Define complexity_penalty_rate
    #return {'rmse': fitness_rmse + complexity_penalty, 'mae': fitness_mae, 'mse': fitness_mse}

    #return fitness_score

# Track best fitness score per generation
best_fitness_scores = []

# Initialize arrays to store the best RMSE and MAE scores
best_rmse_scores = []
best_mae_scores = []
best_mse_scores = []


previous_best_score = float('inf')
# Early stopping parameters
stagnation_threshold = 10  # Number of generations without improvement
stagnation_counter = 0  # Counter for stagnation

diversity_scores = []

# Timesteps
initial_timestep = 1000  # Define an initial value for the timestep
current_timestep = initial_timestep  # Define an initial timestep
timestep_increment = 1  # Define how much to increase timesteps each time
stagnation_threshold = 10  # Number of generations to consider for stagnation
increment_interval = 5     # Check for stagnation every 5 generations


    
# Evolutionary loop
for generation in range(n_generations):
    
    # Load and preprocess data with current timestep
    #X = datasets.mackey_glass(current_timestep, sample_len=1000)
    
    fitness_scores = [evaluate_fitness(genome) for genome in genome_population]
    
    #generation_best_score = min(fitness_scores, key=lambda x: x['rmse'])['rmse']
    #best_fitness_scores.append(generation_best_score)
    
    best_rmse = min(fitness_scores, key=lambda x: x['rmse'])['rmse']
    best_mae = min(fitness_scores, key=lambda x: x['mae'])['mae']
    best_mse = min(fitness_scores, key=lambda x: x['mse'])['mse']
    
    # Check for early stopping if the best score doesn't improve
    # if best_rmse >= previous_best_score:
    #     stagnation_counter += 1
    # else:
    #     stagnation_counter = 0
    #     previous_best_score = best_rmse
    
    # if stagnation_counter >= 10:  # stop if no improvement in 10 generations
    #     print(f"Early stopping at generation {generation} due to lack of improvement.")
    #     break
    
    # Early stopping logic
    # if fitness_scores and fitness_scores[0]['rmse'] < previous_best_score:
    #     previous_best_score = fitness_scores[0]['rmse']
    #     stagnation_counter = 0
    # else:
    #     stagnation_counter += 1

    # if stagnation_counter >= stagnation_threshold:
    #     print(f"\nEarly stopping at generation {generation} due to lack of improvement.")
    #     break
    
            
    # Logic to increase timestep
    if should_increase_timestep(generation, best_fitness_scores, stagnation_threshold, increment_interval):
        current_timestep += timestep_increment
        print(f"Increasing timestep to {current_timestep}")
    # if should_increase_timestep(generation, best_fitness_scores, 10, 5):
    #     n_timesteps += 1  # Increase complexity
    #     X = datasets.mackey_glass(n_timesteps=n_timesteps, sample_len=n_timesteps)
    #     train_end = int(len(X) * 0.7)
    #     test_start = train_end + 1
    
    
    
    best_rmse_scores.append(best_rmse)
    best_mae_scores.append(best_mae)
    best_mse_scores.append(best_mse)
    
    #best_fitness_scores.append(best_rmse)

    #print(f"Generation {generation}: Best Fitness Score: {generation_best_score}")
    
    
    
    
    selected_genomes = select_best_genomes(genome_population, fitness_scores)
    
    # Instead of visualize_genome(selected_genomes), use:
    best_genome = select_best_genomes(genome_population, fitness_scores, 1)[0]  # Get the best genome
    visualize_genome(best_genome)  # Visualize the best genome
    
    # Calculate and record the population's genetic diversity for this generation
    #current_diversity_score = calculate_diversity_score(genome_population)
    #diversity_scores.append(current_diversity_score)
    #print(f"Generation {generation}: Diversity Score: {current_diversity_score}")

    
    # Update the call to 'reproduce' to include node counts
    #new_population = reproduce(selected_genomes, population_size, mutation_probability, num_input_nodes, num_output_nodes, num_elites)
    #genome_population = new_population
    genome_population = reproduce(selected_genomes, population_size, mutation_probability, num_input_nodes, num_output_nodes, num_elites)
    
    # Select a genome for visualization
    genome_for_visualization = copy.deepcopy(random.choice(genome_population))
    visualize_genome(genome_for_visualization)  # Visualize before mutation

    # Mutate and visualize
    mutated_genome = reproduce([genome_for_visualization], 1, mutation_probability, num_input_nodes, num_output_nodes, 0)[0]
    visualize_genome(mutated_genome)  # Visualize after mutation


    # Correct file path for logging
    #log_path = "/Users/chaitravshetty/Downloads/Advanced-Genomes-for-Evolutionary-Computing-main 3/hierarchical_genomes/evolution_log.txt"
    log_path = "evolution_log.txt"
    log_generation_results(generation, selected_genomes, fitness_scores, log_file=log_path)

# Perform post-experiment analysis with the correct file path
#analyze_log_path = "/Users/chaitravshetty/Downloads/Advanced-Genomes-for-Evolutionary-Computing-main 3/hierarchical_genomes/evolution_log.txt"
analyze_log_path = "evolution_log.txt"
analyze_results(log_file=analyze_log_path, best_rmse_scores=best_rmse_scores, best_mae_scores=best_mae_scores, best_mse_scores=best_mse_scores)

Warning: Mismatch in the number of generations and recorded scores.


Generation 0: Best RMSE Score: 0.026953289967973144, Best MAE Score: 0.0210699678639249, Best MSE Score: 0.0007264798400976417
Generation 1: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 2: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 3: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 4: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 5: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 6: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 7: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 8: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 9: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 10: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 11: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 12: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 13: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 14: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 15: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 16: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 17: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 18: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 19: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 20: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 21: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 22: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 23: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 24: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 25: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 26: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 27: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 28: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 29: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 30: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 31: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 32: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 33: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 34: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 35: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 36: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 37: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 38: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 39: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 40: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 41: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 42: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 43: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 44: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 45: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 46: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 47: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 48: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 49: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 50: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 51: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 52: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 53: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 54: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 55: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 56: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 57: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 58: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 59: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 60: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 61: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 62: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 63: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 64: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 65: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 66: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 67: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 68: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 69: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 70: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 71: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 72: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 73: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 74: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 75: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 76: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 77: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 78: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 79: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 80: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 81: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 82: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 83: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 84: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 85: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 86: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 87: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 88: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 89: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 90: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 91: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 92: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 93: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 94: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 95: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 96: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 97: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 98: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 99: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 0: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 1: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 2: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 3: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 4: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 5: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 0: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 1: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 2: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 3: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 4: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 5: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 6: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 7: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 8: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 9: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 10: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 11: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 12: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 13: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 14: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 15: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 16: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 17: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 18: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 19: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 20: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 21: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 22: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 23: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 24: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 25: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 26: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 27: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 28: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 29: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 30: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 31: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 32: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 33: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 34: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 35: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 36: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 37: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 38: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 39: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 40: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 41: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 42: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 43: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 44: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 45: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 46: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 47: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 48: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 49: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 50: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 51: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 52: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 53: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 54: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 55: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 56: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 57: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 58: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 59: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 60: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 61: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 62: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 63: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 64: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 65: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 66: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 67: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 68: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 69: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 70: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 71: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 72: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 73: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 74: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 75: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 76: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 77: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 78: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 79: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 80: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 81: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 82: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 83: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 84: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 85: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 86: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 87: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 88: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 89: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 90: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 91: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 92: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806
Generation 93: Best RMSE Score: 0.02913240278653617, Best MAE Score: 0.022185245838350943, Best MSE Score: 0.0008486968921169806


Average top RMSE score: 0.029121507222443353
Average top MAE score: 0.022179669448478812
Average top MSE score: 0.0008480858068568839